© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20841
    Prev
    Next
    INDEX
    Explanations

    lists of items related to different categories like fashion, food, countries, and intolerance

    oai_token-act-pair · gpt-3.5-turbo

    diverse categories of products and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.79
     tremend
    -0.71
    conom
    -0.67
    ¦
    -0.67
    ¬¼
    -0.66
    ight
    -0.65
     proble
    -0.64
    tsky
    -0.64
     guiActiveUn
    -0.61
    chwitz
    -0.59
    POSITIVE LOGITS
     etc
    1.36
    etc
    0.94
     aka
    0.73
     respectively
    0.70
     Kinnikuman
    0.69
     huh
    0.68
     Jr
    0.68
     preferably
    0.67
     alas
    0.66
    anwhile
    0.66
    Activations Density 1.000%

    No Known Activations